Microsoft Microsoft Certifications DP-100 Questions & Answers

• Question 191:

  You are making use of the Azure Machine Learning to designer construct an experiment.

  After dividing a dataset into training and testing sets, you configure the algorithm to be Two-Class Boosted Decision Tree.

  You are preparing to ascertain the Area Under the Curve (AUC).

  Which of the following is a sequential combination of the models required to achieve your goal?

  A. Train, Score, Evaluate.

  B. Score, Evaluate, Train.

  C. Evaluate, Export Data, Train.

  D. Train, Score, Export Data.

  Correct Answer: A

• Question 192:

  You create a binary classification model. The model is registered in an Azure Machine Learning workspace. You use the Azure Machine Learning Fairness SDK to assess the model fairness.

  You develop a training script for the model on a local machine.

  You need to load the model fairness metrics into Azure Machine Learning studio.

  What should you do?

  A. Implement the download_dashboard_by_upload_idfunction

  B. Implement the create_group_metric_setfunction

  C. Implement the upload_dashboard_dictionaryfunction

  D. Upload the training script

  Correct Answer: C

  import azureml.contrib.fairness package to perform the upload:

  from azureml.contrib.fairness import upload_dashboard_dictionary, download_dashboard_by_upload_id

  Reference:

  https://docs.microsoft.com/en-us/azure/machine-learning/how-to-machine-learning-fairness-aml

• Question 193:

  You have a dataset that includes confidential data. You use the dataset to train a model.

  You must use a differential privacy parameter to keep the data of individuals safe and private.

  You need to reduce the effect of user data on aggregated results.

  What should you do?

  A. Decrease the value of the epsilon parameter to reduce the amount of noise added to the data

  B. Increase the value of the epsilon parameter to decrease privacy and increase accuracy

  C. Decrease the value of the epsilon parameter to increase privacy and reduce accuracy

  D. Set the value of the epsilon parameter to 1 to ensure maximum privacy

  Correct Answer: C

  Differential privacy tries to protect against the possibility that a user can produce an indefinite number of reports to eventually reveal sensitive data. A value known as epsilon measures how noisy, or private, a report is. Epsilon has an inverse relationship to noise or privacy. The lower the epsilon, the more noisy (and private) the data is.

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/concept-differential-privacy

• Question 194:

  You train and register a machine learning model. You create a batch inference pipeline that uses the model to generate predictions from multiple data files.

  You must publish the batch inference pipeline as a service that can be scheduled to run every night.

  You need to select an appropriate compute target for the inference service.

  Which compute target should you use?

  A. Azure Machine Learning compute instance

  B. Azure Machine Learning compute cluster

  C. Azure Kubernetes Service (AKS)-based inference cluster

  D. Azure Container Instance (ACI) compute target

  Correct Answer: B

  Azure Machine Learning compute clusters is used for Batch inference. Run batch scoring on serverless compute. Supports normal and low-priority VMs. No support for real-time inference.

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/concept-compute-target

• Question 195:

  You are planning to make use of Azure Machine Learning designer to train models. You need choose a suitable compute type.

  Recommendation: You choose Compute cluster. Will the requirements be satisfied?

  A. Yes

  B. No

  Correct Answer: A

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-attach-compute-studio

• Question 196:

  You are planning to make use of Azure Machine Learning designer to train models.

  You need choose a suitable compute type.

  Recommendation: You choose Attached compute.

  Will the requirements be satisfied?

  A. Yes

  B. No

  Correct Answer: B

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-attach-compute-studio

• Question 197:

  You are planning to make use of Azure Machine Learning designer to train models.

  You need choose a suitable compute type.

  Recommendation: You choose Inference cluster.

  Will the requirements be satisfied?

  A. Yes

  B. No

  Correct Answer: B

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-attach-compute-studio

• Question 198:

  You are in the process of constructing a deep convolutional neural network (CNN). The CNN will be used for image classification.

  You notice that the CNN model you constructed displays hints of overfitting.

  You want to make sure that overfitting is minimized, and that the model is converged to an optimal fit.

  Which of the following is TRUE with regards to achieving your goal?

  A. You have to add an additional dense layer with 512 input units, and reduce the amount of training data.

  B. You have to add L1/L2 regularization, and reduce the amount of training data.

  C. You have to reduce the amount of training data and make use of training data augmentation.

  D. You have to add L1/L2 regularization, and make use of training data augmentation.

  E. You have to add an additional dense layer with 512 input units, and add L1/L2 regularization.

  Correct Answer: B

  B: Weight regularization provides an approach to reduce the overfitting of a deep learning neural network model on the training data and improve the performance of the model on new data, such as the holdout test set. Keras provides a weight regularization API that allows you to add a penalty for weight size to the loss function.

  Three different regularizer instances are provided; they are:

  L1: Sum of the absolute weights.

  L2: Sum of the squared weights.

  L1L2: Sum of the absolute and the squared weights.

  Because a fully connected layer occupies most of the parameters, it is prone to overfitting. One method to reduce overfitting is dropout. At each training stage, individual nodes are either "dropped out" of the net with probability 1-p or kept with

  probability p, so that a reduced network is left; incoming and outgoing edges to a dropped-out node are also removed.

  By avoiding training all nodes on all training data, dropout decreases overfitting.

  Reference:

  https://machinelearningmastery.com/how-to-reduce-overfitting-in-deep-learning-with-weight-regularization/

  https://en.wikipedia.org/wiki/Convolutional_neural_network

• Question 199:

  You make use of Azure Machine Learning Studio to create a binary classification model.

  You are preparing to carry out a parameter sweep of the model to tune hyperparameters. You have to make sure that the sweep allows for every possible combination of hyperparameters to be iterated. Also, the computing resources needed

  to carry out the sweep must be reduced.

  Which of the following actions should you take?

  A. You should consider making use of the Selective grid sweep mode.

  B. You should consider making use of the Measured grid sweep mode.

  C. You should consider making use of the Entire grid sweep mode.

  D. You should consider making use of the Random grid sweep mode.

  Correct Answer: D

  Maximum number of runs on random grid: This option also controls the number of iterations over a random sampling of parameter values, but the values are not generated randomly from the specified range; instead, a matrix is created of all possible combinations of parameter values and a random sampling is taken over the matrix. This method is more efficient and less prone to regional oversampling or undersampling.

  If you are training a model that supports an integrated parameter sweep, you can also set a range of seed values to use and iterate over the random seeds as well. This is optional, but can be useful for avoiding bias introduced by seed selection.

  C: Entire grid: When you select this option, the module loops over a grid predefined by the system, to try different combinations and identify the best learner. This option is useful for cases where you don't know what the best parameter settings might be and want to try all possible combination of values.

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/tune-model-hyperparameters

• Question 200:

  You make use of Azure Machine Learning Studio to develop a linear regression model. You perform an experiment to assess various algorithms. Which of the following is an algorithm that reduces the variances between actual and predicted values?

  A. Fast Forest Quantile Regression

  B. Poisson Regression

  C. Boosted Decision Tree Regression

  D. Linear Regression

  Correct Answer: C

  Mean absolute error (MAE) measures how close the predictions are to the actual outcomes; thus, a lower score is better.

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/boosted-decision-tree-regression https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/evaluate-model https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/linear-regression